What problem does it solve? Accessing many AI models normally requires managing separate provider APIs, GPUs, and credentials. This Skill lets you run 150+ hosted AI apps—image generation, video creation, TTS, search, 3D, and social automation—through a single infsh CLI without any GPU or per-provider setup. ## Core Features & Use Cases - App Discovery: Search the inference.sh catalog with infsh app list --search to find the correct app ID before running anything. - Media Generation: Run apps like FLUX, Veo, Seedance, Gemini image, and OmniHuman with JSON inputs, including automatic upload of local files. - Structured Output: Use the --json flag to get machine-readable results with media URLs, and track long-running tasks via infsh task get. - Use Case: A user asks for a short drone-style video clip. You search for video apps, run google/veo-3-1-fast with a JSON prompt, and return the generated video URL for inline display. ## Quick Start Ask the agent to generate an image of a sunset over mountains using inference.sh, and it will search for the right app, run it with the infsh CLI, and return the image URL.
